A field guide to the mistakes your mind makes — an open, adversarial behavioural-bias engine (web + MCP). Runs no model; audits via your own AI.
claude mcp add irrational -- npx -y wrangler{
"mcpServers": {
"irrational": {
"command": "npx",
"args": ["-y", "wrangler"]
}
}
}MCP Servers overview
# Irrational
**A field guide to the mistakes your mind makes, and an open, adversarial behavioural-bias engine you can call from your own AI or any MCP agent.**
<p align="center">
<a href="https://irrational.pages.dev"><img src="public/og.png" alt="Irrational: a field guide to the mistakes your mind makes, and an engine that audits your decisions" width="720" /></a>
</p>
[](https://irrational.pages.dev)
[](https://registry.modelcontextprotocol.io/v0/servers?search=irrational)
[](https://github.com/urbanmorph/irrational/actions/workflows/ci.yml)
[](LICENSE)
[](CONTRIBUTING.md)
→ **[irrational.pages.dev](https://irrational.pages.dev)** · [Field guide](https://irrational.pages.dev/biases) · [Connect via MCP](https://irrational.pages.dev/mcp) · [Sources](https://irrational.pages.dev/sources)
Irrational **runs no AI model.** It provides the curated adversarial framework, a 22-bias catalogue, and a stateless scaffold, delivered as a public field guide and an open MCP tool, and the reasoning is done by whatever model you or your agent already have. **No API keys. No stored decisions. Nothing leaves you.**
A frontier model already knows the biases, so the value isn't informational; it's behavioural. A plain LLM is trained to agree, while Irrational has a fixed adversarial contract (_assume you're biased, refuse to validate, argue the other side_) that an agent can invoke systematically, even on its own draft reasoning.
## What an audit looks like
> **You:** "We should rewrite our 6-year-old backend from scratch this year, we've already spent two months on a POC that went well, and I'm confident we can finish in six."
> **THE CALL**: Don't greenlight the big-bang rewrite. Carve off the worst module first, with a hard 3-month checkpoint. Confidence the 6-month plan succeeds: ~25%, mostly **sunk cost** + the **planning fallacy**.
>
> **THE AUDIT**: Those "two months on a POC" are gone either way, but they're doing most of the talking _(sunk cost)_. "About six months" is a best-case with no reference class; rewrites of mature systems routinely run 2–3× _(planning fallacy)_…
Verdict-first, every bias tied to your own words, grounded in a cited catalogue. [See the full worked examples →](https://irrational.pages.dev/#engine)
## Add it to your AI
Listed on the **[official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers?search=irrational)** as `io.github.urbanmorph/irrational`. Connect any MCP client to the live endpoint, no install, no keys:
```bash
# Claude Code
claude mcp add --transport http irrational https://irrational.pages.dev/mcp/server
```
…or point any MCP client at `https://irrational.pages.dev/mcp/server`:
```json
{
"mcpServers": {
"irrational": {
"type": "http",
"url": "https://irrational.pages.dev/mcp/server"
}
}
}
```
Tools: `analyze_decision` (the adversarial audit) · `list_biases` · `get_bias`. Pass `language` for a reply in another language, or `structured: true` for parseable JSON.
## What's inside
- **Field guide**: 22 cognitive biases grouped by Buster Benson's four problems the brain solves, each with the question that breaks its spell and a **verified citation**.
- **The engine**: an MCP server exposing `analyze_decision`, `list_biases`, `get_bias`. `analyze_decision` returns a verdict-first _directive_ your model executes. The discipline is ours; the reasoning is yours.
- **The web forge**: type a decision; it assembles the adversarial prompt in your browser and hands off to _your_ AI. No model runs here.
- **Pen-and-paper audit**: the whole method on one [printable page](https://irrational.pages.dev/checklist).
## Stack
Astro (pure static) · Cloudflare Pages · a hand-rolled, dependency-free JSON-RPC MCP endpoint as a [Pages Function](functions/mcp/server.ts). No runtime model, no database. Single source of truth: [`src/data/biases.ts`](src/data/biases.ts) feeds both the web and the MCP.
## Develop
```bash
npm install --ignore-scripts # we don't use image optimization, so skip sharp's native build
npm run dev # http://localhost:4321
npm test # vitest, engine + catalogue (29 tests)
npm run build # static pages
```
The MCP endpoint is a Cloudflare Pages Function, run it locally with `npx wrangler pages dev dist`.
## Contributing
Translations, proposed biases, and worked examples are welcome, see [CONTRIBUTING.md](CONTRIBUTING.md). This project also publishes a public [PDGI scorecard](PDGI.md).
## Licence
Code is **[MIT](LICENSE)**. The bias-catalogue text (definitions, examples, and the curated prose in `src/data/`) is additionally available under **CC-BY-4.0**. Every claim is cited, see [/sources](https://irrational.pages.dev/sources).
Built by [Urban Morph](https://urbanmorph.com).
What people ask about irrational
What is urbanmorph/irrational?
+
urbanmorph/irrational is mcp servers for the Claude AI ecosystem. A field guide to the mistakes your mind makes — an open, adversarial behavioural-bias engine (web + MCP). Runs no model; audits via your own AI. It has 0 GitHub stars and was last updated yesterday.
How do I install irrational?
+
You can install irrational by cloning the repository (https://github.com/urbanmorph/irrational) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is urbanmorph/irrational safe to use?
+
urbanmorph/irrational has not been audited yet by our security agent. Review the original repository on GitHub before using it in production.
Who maintains urbanmorph/irrational?
+
urbanmorph/irrational is maintained by urbanmorph. The last recorded GitHub activity is from yesterday, with 0 open issues.
Are there alternatives to irrational?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy irrational to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/urbanmorph-irrational)<a href="https://claudewave.com/repo/urbanmorph-irrational"><img src="https://claudewave.com/api/badge/urbanmorph-irrational" alt="Featured on ClaudeWave: urbanmorph/irrational" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。